A second-order-like optimizer with adaptive gradient scaling for deep learning
In this empirical article, we introduce INNAprop, an optimization algorithm that combines the INNA method with the RMSprop adaptive gradient scaling. It leverages second-order information and rescaling while keeping the memory requirements of standard DL methods as AdamW or SGD with momentum. After giving geometrical insights, we evaluate INNAprop on CIFAR-10, Food101, and ImageNet with ResNets, VGG, DenseNet, and ViT, and on GPT-2 (OpenWebText) train from scratch and with LoRA fine-tuning (E2E). INNAprop consistently matches or outperforms AdamW both in training speed and accuracy, with minimal hyperparameter tuning in large-scale settings. Our code is publicly available at \url{https://github.com/innaprop/innaprop}.
Code (1)
Tasks
Image ClassificationLanguage ModellingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information Analysis
First-order optimization methods remain the standard for training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by preconditioning the stochastic gradient with a diagonal mat…
Computational Efficiencyimage-classificationImage ClassificationLanguage Modeling+2AdaFisher: Adaptive Second Order Optimization via Fisher Information
First-order optimization methods are currently the mainstream in training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by employing the diagonal matrix preconditioning of th…
Computational Efficiencyimage-classificationImage ClassificationLanguage Modeling+1Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective
Adaptive gradient optimizers like Adam(W) are the default training algorithms for many deep learning architectures, such as transformers. Their diagonal preconditioner is based on the gradient outer product which is inco…
Second-order methodsMomentum Centering and Asynchronous Update for Adaptive Gradient Methods
We propose ACProp (Asynchronous-centering-Prop), an adaptive optimizer which combines centering of second momentum and asynchronous update (e.g. for $t$-th update, denominator uses information up to step $t-1$, while num…
image-classificationImage ClassificationThe Unified Balance Theory of Second-Moment Exponential Scaling Optimizers in Visual Tasks
We have identified a potential method for unifying first-order optimizers through the use of variable Second-Moment Exponential Scaling(SMES). We begin with back propagation, addressing classic phenomena such as gradient…